picasso: Pathwise Calibrated Sparse Shooting Algorithm

Share:

Computationally efficient tools for fitting generalized linear model with convex or non-convex penalty. Users can enjoy the superior statistical property of non-convex penalty such as SCAD and MCP which has significantly less estimation error and overfitting compared to convex penalty such as lasso and ridge. Computation is handled by multi-stage convex relaxation and the PathwIse CAlibrated Sparse Shooting algOrithm (PICASSO) which exploits warm start initialization, active set updating, and strong rule for coordinate preselection to boost computation, and attains a linear convergence to a unique sparse local optimum with optimal statistical properties. The computation is memory-optimized using the sparse matrix output.

Author
Jason Ge, Xingguo Li, Mengdi Wang, Tong Zhang, Han Liu and Tuo Zhao
Date of publication
2016-10-06 20:14:19
Maintainer
Jason Ge <jiange@princeton.edu>
License
GPL-2
Version
0.5.4

View on CRAN

Man pages

coef.gaussian
Extract Model Coefficients for an object with S3 class...
coef.logit
Extract Model Coefficients for an object with S3 class...
coef.poisson
Extract Model Coefficients for an object with S3 class...
eyedata
The Bardet-Biedl syndrome Gene expression data from Scheetz...
picasso
PathwIse CAlibrated Sparse Shooting algOrithm (PICASSO)
picasso-package
PICASSO: PathwIse CAlibrated Sparse Shooting algOrithm
plot.gaussian
Plot Function for "gaussian"
plot.logit
Plot Function for "logit"
plot.poisson
Plot Function for "poisson"
predict.gaussian
Prediction for an object with S3 class '"gaussian"'
predict.logit
Prediction for an object with S3 class '"logit"'
predict.poisson
Prediction for an object with S3 class '"poisson"'
print.gaussian
Print Function for an object with S3 class '"gaussian"'
print.logit
Print Function for an object with S3 class '"logit"'
print.poisson
Print Function for an object with S3 class 'poisson'

Files in this package

picasso
picasso/inst
picasso/inst/doc
picasso/inst/doc/vignette.Rnw
picasso/inst/doc/PICASSO.pdf
picasso/inst/doc/vignette.pdf
picasso/src
picasso/src/IRLS_solver.c
picasso/src/mathutils.c
picasso/src/mathutils.h
picasso/src/picasso_gaussian_cov.c
picasso/src/picasso_poisson.c
picasso/src/IRLS_solver.h
picasso/src/picasso_gaussian_naive.c
picasso/src/picasso_logit.c
picasso/NAMESPACE
picasso/data
picasso/data/eyedata.rda
picasso/data/datalist
picasso/R
picasso/R/picasso.R
picasso/R/poisson_solver.R
picasso/R/picasso.poisson.R
picasso/R/logit_solver.R
picasso/R/picasso.gaussian.R
picasso/R/picasso.logit.R
picasso/R/gaussian_solver.R
picasso/vignettes
picasso/vignettes/vignette.Rnw
picasso/vignettes/PICASSO.pdf
picasso/MD5
picasso/build
picasso/build/vignette.rds
picasso/DESCRIPTION
picasso/man
picasso/man/print.poisson.Rd
picasso/man/coef.logit.Rd
picasso/man/picasso.Rd
picasso/man/coef.poisson.Rd
picasso/man/print.gaussian.Rd
picasso/man/coef.gaussian.Rd
picasso/man/eyedata.Rd
picasso/man/predict.poisson.Rd
picasso/man/predict.gaussian.Rd
picasso/man/print.logit.Rd
picasso/man/predict.logit.Rd
picasso/man/plot.logit.Rd
picasso/man/plot.gaussian.Rd
picasso/man/plot.poisson.Rd
picasso/man/picasso-package.Rd